© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1284
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĩãĤĬ
    -0.07
    nsk
    -0.07
    (unique
    -0.07
    çĿĢæĪij们çļĦ
    -0.07
    馴
    -0.07
    oca
    -0.07
    LBL
    -0.07
    æģ¥
    -0.07
     gul
    -0.07
    åĨįä¹Łä¸į
    -0.07
    POSITIVE LOGITS
     Proto
    0.10
    Proto
    0.10
    åIJİä¸ĸ
    0.09
    åħĪ秦
    0.09
    åı¤äºº
    0.09
    proto
    0.08
    æĹ©æľŁ
    0.08
    è§ģäºİ
    0.08
    early
    0.08
    å½ĵæŶçļĦ
    0.08
    Activations Density 0.000%

    No Known Activations